Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 10962
    Prev
    Next
    INDEX
    Explanations

    the word "the" or phrases closely related to it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.61
    Hozzáférés
    -0.54
     voilà
    -0.52
    ankan
    -0.51
    ligg
    -0.51
    cokinetics
    -0.49
     διά
    -0.48
    plotlib
    -0.47
    lwjgl
    -0.46
    pushFollow
    -0.46
    POSITIVE LOGITS
    FROM
    1.27
     FROM
    1.23
     från
    1.08
     From
    1.07
    From
    1.03
     from
    1.03
    from
    0.97
    desde
    0.97
     từ
    0.94
    getFrom
    0.90
    Activations Density 0.126%

    No Known Activations